SKILLEMALL.ai
GitHub ↗ RU Sign in

CC local-llm

Use when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead request, understanding RAM/speed tradeoffs, or wiring a new script to the local inference endpoint.

coco-research/coco Agent Skills author: coco-research 1 file body ≈ 7 866 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Use when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead…

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
79/100
safety, quality, tests
Safety 60%
84
Quality 40%
71
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-persistence SKILL.md:20
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
    | **mlx-dspark** | 8090 | Production -- everything `build_local.py` and any script under `systems/superintelligence/*` talks to | `launchd` (`~/Library/LaunchAgents/com.local.mlx-dspark.plist`) |
    table
  • medium Dangerous commands cmd-persistence SKILL.md:34
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - `~/Library/LaunchAgents/com.local.mlx-dspark.plist` -- the server's LaunchAgent
    quoted
  • medium Dangerous commands cmd-persistence SKILL.md:36
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - `~/Library/LaunchAgents/com.local.mlx-dspark-idle-watcher.plist` -- the
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:103
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `Qwen…ion`) is a **hybrid attention** model: only 16 of
    quoted

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7866 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "domain"

Process rating: all ten parameters 50/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 6 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 70Execution cost. Instruction body is 7866 tokens
  • 85Steps. 29 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 15 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 258: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 29 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.